[PATCH] D53930: [AMDGPU] Fix the new atomic optimizer in pixel shaders.

[Nicolai Hähnle via Phabricator via llvm-commits]

nhaehnle accepted this revision.
nhaehnle added inline comments.
This revision is now accepted and ready to land.


================
Comment at: test/CodeGen/AMDGPU/atomic_optimizations_pixelshader.ll:24
+  %cond1 = call i1 @llvm.amdgcn.wqm.vote(i1 true)
+
+  %old = call i32 @llvm.amdgcn.buffer.atomic.add(i32 5, <4 x i32> %inout, i32 0, i32 0, i1 0)
----------------
Please remove the empty lines in this test and below.


================
Comment at: test/CodeGen/AMDGPU/atomic_optimizations_pixelshader.ll:41
+; GCN-LABEL: add_i32_varying:
+; GFX8MORE: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], exec_lo, 0
+; GFX8MORE: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], exec_hi, v[[mbcnt_lo]]
----------------
Why are there no check lines for GFX7LESS? What's the difference?


https://reviews.llvm.org/D53930